Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     index
    0.57
     res
    0.53
     pow
    0.47
     duc
    0.46
     unters
    0.46
     apoyo
    0.45
     apoio
    0.45
    ذي
    0.44
    ريق
    0.44
     خمسه
    0.44
    POSITIVE LOGITS
    cycled
    0.55
    anneer
    0.46
     கடற்க
    0.45
    ánt
    0.43
     Williamsburg
    0.43
    arendon
    0.42
     మద్యం
    0.42
    fait
    0.42
     अचानक
    0.41
     स्कूल
    0.41
    Act Density 0.037%

    No Known Activations